English
Related papers

Related papers: Dynamic Multi-Reward Weighting for Multi-Style Con…

200 papers

We present a method to control a text-to-image generative model to produce training data useful for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Teresa Yeo , Andrei Atanov , Harold Benoit , Aleksandr Alekseev , Ruchira Ray , Pooya Esmaeil Akhoondi , Amir Zamir

This research explores strategies for steering the output of large language models (LLMs) towards specific styles, such as sentiment, emotion, or writing style, by adding style vectors to the activations of hidden layers during text…

Computation and Language · Computer Science 2024-02-05 Kai Konen , Sophie Jentzsch , Diaoulé Diallo , Peer Schütt , Oliver Bensch , Roxanne El Baff , Dominik Opitz , Tobias Hecking

Dynamic Reinforcement Learning (Dynamic RL), proposed in this paper, directly controls system dynamics, instead of the actor (action-generating neural network) outputs at each moment, bringing about a major qualitative shift in…

Machine Learning · Computer Science 2025-02-17 Katsunari Shibata

We consider the task of word-level language modeling and study the possibility of combining hidden-states-based short-term representations with medium-term representations encoded in dynamical weights of a language model. Our work extends…

Computation and Language · Computer Science 2018-03-29 Thomas Wolf , Julien Chaumond , Clement Delangue

Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes. Modeling…

Computation and Language · Computer Science 2016-09-30 Jiwei Li , Will Monroe , Alan Ritter , Michel Galley , Jianfeng Gao , Dan Jurafsky

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Computation and Language · Computer Science 2025-05-27 Jinyan Su , Claire Cardie

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Computation and Language · Computer Science 2024-10-25 Vaskar Nath , Dylan Slack , Jeff Da , Yuntao Ma , Hugh Zhang , Spencer Whitehead , Sean Hendryx

Reward design is a key component of deep reinforcement learning, yet some tasks and designer's objectives may be unnatural to define as a scalar cost function. Among the various techniques, formal methods integrated with DRL have garnered…

Artificial Intelligence · Computer Science 2023-10-24 Jiangwei Wang , Shuo Yang , Ziyan An , Songyang Han , Zhili Zhang , Rahul Mangharam , Meiyi Ma , Fei Miao

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify…

Neural and Evolutionary Computing · Computer Science 2025-05-26 Rishi Hazra , Alkis Sygkounas , Andreas Persson , Amy Loutfi , Pedro Zuidberg Dos Martires

Current large-scale language models can be politically biased as a result of the data they are trained on, potentially causing serious problems when they are deployed in real-world settings. In this paper, we describe metrics for measuring…

Computation and Language · Computer Science 2021-05-03 Ruibo Liu , Chenyan Jia , Jason Wei , Guangxuan Xu , Lili Wang , Soroush Vosoughi

Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Fanyue Wei , Wei Zeng , Zhenyang Li , Dawei Yin , Lixin Duan , Wen Li

Controllable code generation, the ability to synthesize code that follows a specified style while maintaining functionality, remains a challenging task. We propose a two-stage training framework combining contrastive learning and…

Artificial Intelligence · Computer Science 2026-01-27 Dutao Zhang , Nicolas Rafael Arroyo Arias , YuLong He , Sergey Kovalchuk

We study the task of long-form opinion text generation, which faces at least two distinct challenges. First, existing neural generation models fall short of coherence, thus requiring efficient content planning. Second, diverse types of…

Computation and Language · Computer Science 2021-06-03 Xinyu Hua , Ashwin Sreevatsa , Lu Wang

Reward engineering, the manual specification of reward functions to induce desired agent behavior, remains a fundamental challenge in multi-agent reinforcement learning. This difficulty is amplified by credit assignment ambiguity,…

Artificial Intelligence · Computer Science 2026-01-14 Haoran Su , Yandong Sun , Congjia Yu

Multi-aspect controllable text generation is a more challenging and practical task than single-aspect control. Existing methods achieve complex multi-aspect control by fusing multiple controllers learned from single-aspect, but suffer from…

Computation and Language · Computer Science 2022-10-20 Yuxuan Gu , Xiaocheng Feng , Sicheng Ma , Lingyuan Zhang , Heng Gong , Bing Qin

Multi-agent reinforcement learning has drawn increasing attention in practice, e.g., robotics and automatic driving, as it can explore optimal policies using samples generated by interacting with the environment. However, high reward…

Machine Learning · Computer Science 2022-10-17 Jifeng Hu , Yanchao Sun , Hechang Chen , Sili Huang , haiyin piao , Yi Chang , Lichao Sun

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. Due to the difficulty of obtaining high-quality human preference annotations, distilling preferences from generative LLMs has emerged…

Computation and Language · Computer Science 2026-01-21 Hongli Zhou , Hui Huang , Wei Liu , Chenglong Wang , Xingyuan Bu , Lvyuan Han , Fuhai Song , Muyun Yang , Wenhao Jiang , Hailong Cao , Tiejun Zhao

Current approaches for controlling dialogue response generation are primarily focused on high-level attributes like style, sentiment, or topic. In this work, we focus on constrained long-term dialogue generation, which involves more…

Computation and Language · Computer Science 2022-05-17 Ramya Ramakrishnan , Hashan Buddhika Narangodage , Mauro Schilman , Kilian Q. Weinberger , Ryan McDonald

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Hengjia Li , Liming Jiang , Qing Yan , Yizhi Song , Hao Kang , Zichuan Liu , Xin Lu , Boxi Wu , Deng Cai